© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 79646
    Prev
    Next
    INDEX
    Explanations

    commentary

    np_acts-logits-general · gemini-2.5-flash-lite

    who works, this is, current priorities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    るのは
    0.51
    CUL
    0.50
    じて
    0.50
    人に
    0.45
     Bül
    0.44
    cm
    0.44
    7
    0.43
    Whether
    0.43
    ંને
    0.43
    ফিক
    0.42
    POSITIVE LOGITS
     कमेंट
    0.50
    }\
    0.47
     为
    0.46
     powie
    0.44
    borg
    0.44
     komentar
    0.43
     memiliki
    0.43
     commentary
    0.43
    ्ञ
    0.43
     sukses
    0.42
    Activations Density 0.000%

    No Known Activations